Performance enhancement of stepped basin solar still based on OSELM with traversal tree for higher energy adaptive control

Abstract

A basin solar still precision design is regularly not reachable. To solve this issue, the basin area is coated with a nanolayer which allows to stimulate and control the multifaceted of the fast evaporations of physiognomies. The use of adaptive neural network-based approaches leads to better design cause permits detecting the conjunction, gigantic period feed, lower performances parameters which can be detrimental to system production. Further, an online Sequential Extreme Learning Machine (OSELM) system can be used to obtain the latest solar still based on adaptive control. Here, the solar still has been created at physical scale activity for haste of energy absorption. The performance of solar still is defined by the uniform occurrence with time series of dynamics transfer from basin liner to saline water. The feasibility scheme to authenticate was studied by applying calculation to the extensive heat transfer process. The furious SiO2/TiO2 nanoparticles used for the stepped basin solar still (SBSS) efficiency shows an increase of performances by 37.69% and 49.21%, respectively using 20% and 30% of SiO2/TiO2 coating. It is comparable higher when equated against an SBSS coating either SiO2 or TiO2, and/or no nanoparticles coatings. The binary search tree enabled to find the optimal cost for the solar still investigated and obtaining a superior design with higher performances.